MIST: A Simple and Scalable End-To-End 3D Medical Imaging Segmentation Framework
This provides a tool for researchers in medical imaging to ensure reproducible and fair comparisons of segmentation methods, though it is incremental as it builds on existing deep learning approaches.
The authors tackled the lack of standardized tools for comparing deep learning-based medical imaging segmentation methods by introducing MIST, a framework that standardizes training, testing, and evaluation pipelines, and demonstrated its efficacy on the BraTS dataset with accurate segmentation masks and scalability across multiple GPUs.
Medical imaging segmentation is a highly active area of research, with deep learning-based methods achieving state-of-the-art results in several benchmarks. However, the lack of standardized tools for training, testing, and evaluating new methods makes the comparison of methods difficult. To address this, we introduce the Medical Imaging Segmentation Toolkit (MIST), a simple, modular, and end-to-end medical imaging segmentation framework designed to facilitate consistent training, testing, and evaluation of deep learning-based medical imaging segmentation methods. MIST standardizes data analysis, preprocessing, and evaluation pipelines, accommodating multiple architectures and loss functions. This standardization ensures reproducible and fair comparisons across different methods. We detail MIST's data format requirements, pipelines, and auxiliary features and demonstrate its efficacy using the BraTS Adult Glioma Post-Treatment Challenge dataset. Our results highlight MIST's ability to produce accurate segmentation masks and its scalability across multiple GPUs, showcasing its potential as a powerful tool for future medical imaging research and development.